CAS-Spawned ScienceClaw Launches AutoProject: AI Research Agents Move From Tasks to Whole Projects
量子位 · wechat · 2026-08-24
ScienceClaw, the research agent from CAS-incubated Zhongke Zidong Taichu, has unveiled AutoProject, a project-level autonomous research engine that moves AI from executing isolated tasks to owning full scientific projects: given only a research goal, the system handles planning, task decomposition, long-horizon execution, evidence verification, dynamic repair and result consolidation.
The engine has three core layers: Project2Task generates executable task networks with flexible topologies; TaskExecutor sustains long-horizon autonomous execution with anomaly handling and experiment re-runs; and EviGraph, an evidence-graph verification system, checks cross-task logical consistency, scoring 0.865 on ARCBenchML versus a 0.596 best baseline, with ClaimSupportRate up 40.74%. The team stresses "autonomous research is not unmanned research" — researchers can intervene at any point. Built on the Zidong Taichu multimodal LLM and a hierarchical multi-agent architecture, ScienceClaw covers life sciences, materials, chemistry, physics and astronomy.
More from Apps
- Dreamina generates 30s AI video for $0.78, 76% cheaper than alternatives — HeyAmit_ · 2026-08-24
- Dreamina Undercuts Rivals with 76% Lower Pricing — Div_pradeep · 2026-08-24
- Director's note triggers tedious post-production detour, testing AI tool for fix — HeyAmit_ · 2026-08-24
- 39 Custom CSS Cursors Library Includes AI Prompts — Div_pradeep · 2026-08-24
- Tip: Start a new chat for new tasks to save unnecessary context — eyishazyer · 2026-08-24
- ZenReel launches AI tool to turn ideas into short-form videos with scripts and visuals — Shruti_0810 · 2026-08-24